【摘要】 针对经编企业目前存在的采集繁杂的数据，但缺少科学地对数据进行挖掘和分析的问题，运用C5.0决策树算法，对影响经编车间机器运行效率的多项因素，如原料类型、机器型号、挡车工号、班次、运行时间、停车次数、室内温度、相对湿度等进行深入分类和研究。对预处理过的19 407条数据，通过计算信息增益率，Boosting算法优化迭代模型，以及枝叶修剪等手段，分析出对机器运行效率影响程度大小排序为：机器型号、运行时间、原料类型、室内温度、相对湿度、班次、挡车工号，并根据决策树模型给出各因素决策方案，有效地提高车间机器的运行效率。更多还原

【Abstract】 Aiming at the problem that warp knitting enterprises currently collect complex data but lack of scientific data mining and analysis, the C5.0 decision tree algorithm is used to analyze the various factors affecting the operating efficiency of warp knitting workshop machines, such as raw material type, machine model, operator number, shift, running time, parking time, indoor temperature, relative humidity and so on. For the 19 407 pieces of data after preprocessing, by calculating the information gain rate, the boosting algorithm to optimize the iterative model, and pruning of branches and leaves, the order of the impact on the operating efficiency of the machine is analyzed as follows: machine model, running time, raw material type, indoor temperature, relative humidity, shift,operator number, and the decision-making scheme of each factor is given according to the decision tree model,which effectively improves the operating efficiency of the workshop machines.更多还原